44 citations · 96 across the 11 of their papers we have counts for
16 papers
SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentation
Anja Delić, Jurica Runtas, Marin Oršić +2
Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems that depend on scene parsing i…
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Ivan Sabolić, Marin Oršić, Josip Šarić +1
Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulner…
EAST: Early Action Prediction Sampling Strategy with Token Masking
Iva Sović, Ivan Martinović, Marin Oršić
Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and e…
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
Ivan Martinović, Josip Šarić, Marin Oršić +2
Pixel-level annotation is expensive and time-consuming. Semi-supervised segmentation methods address this challenge by learning models on few labeled images alongside a large corpu…
Weakly supervised training of universal visual concepts for multi-domain semantic segmentation
Petra Bevandić, Marin Oršić, Ivan Grubišić +2
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on multiple datasets becomes a method of choice towards strong ge…
Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation
Josip Šarić, Marin Oršić, Siniša Šegvić
Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or remote sensing. Many of these applications require f…
Multi-domain semantic segmentation with overlapping labels
Petra Bevandić, Marin Oršić, Ivan Grubišić +2
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degr…
Revisiting consistency for semi-supervised semantic segmentation
Ivan Grubišić, Marin Oršić, Siniša Šegvić
Semi-supervised learning an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of…
Dense outlier detection and open-set recognition based on training with noisy negative images
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently b…
Multi-domain semantic segmentation with pyramidal fusion
Petra Bevandić, Marin Oršić, Ivan Grubišić +2
We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020. The contest requires submitting the same model to seven benchmarks…
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications. One of the major unsolved problems is to identi…
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
Josip Šarić, Marin Oršić, Tonći Antunović +2
Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driv…
Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings
Borna Bićanić, Marin Oršić, Ivan Marković +2
This paper studies the interplay between kinematics (position and velocity) and appearance cues for establishing correspondences in multi-target pedestrian tracking. We investigate…
In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
Marin Oršić, Ivan Krešo, Petra Bevandić +1
Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve re…
Discriminative out-of-distribution detection for semantic segmentation
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However,…
Robust Semantic Segmentation with Ladder-DenseNet Models
Ivan Krešo, Marin Oršić, Petra Bevandić +1
We present semantic segmentation experiments with a model capable to perform predictions on four benchmark datasets: Cityscapes, ScanNet, WildDash and KITTI. We employ a ladder-sty…